Work

Digital twins in agriculture: A systematic literature review on modeling, semantics, and interoperability

Year: 2026

Type: review

Abstract: The adoption of Digital Twins in agriculture has increased significantly in recent years, driven by advances in sensing technologies, computational modeling, and data-driven analytics. As agricultural systems become increasingly complex and interconnected, the ability to integrate heterogeneous data sources and enable consistent data exchange across platforms has become a critical requirement. However, challenges related to interoperability and data integration continue to hinder the effective deployment of agricultural Digital Twins. This paper presents a Systematic Literature Review on the application of Digital Twins in agriculture, focusing on modeling approaches, semantic representations, and interoperability mechanisms. Following a structured review protocol, studies published between 2016 and January 2026 were retrieved from major scientific digital libraries. The multi-stage screening process reduced an initial dataset of 6,968 records to a final corpus of 62 primary studies. The results show a strong concentration of research in semantic and knowledge modeling, interoperability and integration mechanisms, and analytics-driven decision support. Crop- and plant-oriented Digital Twins dominate the literature, while the digitalization of agricultural machinery and large-scale integrated farming systems remains comparatively limited. The review also identifies key research gaps related to the lack of standardized architectures, limited cross-asset integration, and scarce large-scale field validation. These findings provide a consolidated perspective on the current state of Digital Twin research in agriculture and outline future research directions toward more interoperable and scalable digital agricultural ecosystems.

Source: Smart Agricultural Technology

DOI: 10.1016/j.atech.2026.102283